agentleFS
spencerpaulyspencerpauly/skills-repo/skills/review-pr/SKILL.md

review-pr

Skill25 starsChanged 7 months agoMITView on GitHub

Read a pull request diff like a senior engineer. Flag risk, suggest tests, point out missing edge cases. Use when the user asks to "review PR", "look at this diff", or pastes a GitHub PR URL.

185 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose-ci-failures, docs-loop and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • zerx-labSkill

    diagnose-ci-failures

    Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.

    Also in 3 projects that use this

  • GeiserXSkill

    docs-loop

    Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.

    Also in 3 projects that use this

  • GeiserXSkill

    full-loop

    Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.

    Also in 3 projects that use this

  • n24q02mSkill

    review-delta

    Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

    Also in 3 projects that use this

  • n24q02mSkill

    build-graph

    Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

    Also in 3 projects that use this

  • +7 more from GeiserX

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read a diff the way a thoughtful senior engineer would.

    line 9
  2. Very specific:

    Fetch the diff: If a URL was given, run gh pr diff <number> (or gh pr view <number> --json files,title,body).

    line 18
  3. Distinctive:

    Don't comment on formatting if the repo has a formatter — that's the linter's job.

    line 53
  4. Distinctive:

    Don't suggest renames unless the existing name is genuinely misleading.

    line 54
  5. Distinctive:

    Don't ask the author to "consider" something — either it's a Must-fix, a Should-fix, or it's not in the review.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 178 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review PR

Read a diff the way a thoughtful senior engineer would. Optimize for catching bugs and missing tests, not for nitpicks.

When to use

  • User pastes a GitHub PR URL.
  • User says "review this PR", "what do you think of this diff", "ship-check this".

Steps

  1. Fetch the diff. If a URL was given, run gh pr diff <number> (or gh pr view <number> --json files,title,body). If it's a local branch, git diff main...HEAD.
  2. Read the description first. What is this PR trying to accomplish? Hold that intent in mind for the rest of the review.
  3. Walk the diff in this order:
    1. New files / new entry points (highest risk).
    2. Modified business logic.
    3. Tests.
    4. Configuration, dependencies, infra.
  4. For each substantive change, check the checklist in references/checklist.md.
  5. Write the review in this shape:

    ## Summary
    <one paragraph: what changed, what it's trying to do>
    
    ## Must-fix
    - [ ] <hard bugs, missing error handling, security issues>
    
    ## Should-fix
    - [ ] <missing tests, brittle code, unclear intent>
    
    ## Nits
    - [ ] <style, naming, suggestions — keep these short>
    
    ## Questions
    - <things you genuinely don't understand>
  6. Default posture: approve unless there's a Must-fix. Senior reviewers unblock; they don't gatekeep.

Don't

  • Don't comment on formatting if the repo has a formatter — that's the linter's job.
  • Don't suggest renames unless the existing name is genuinely misleading.
  • Don't ask the author to "consider" something — either it's a Must-fix, a Should-fix, or it's not in the review.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.